Muse Wonder Full: benchmark results
Meta's higher-capability Muse Wonder Full (October 12, 2026), available through paid Muse Code subscriptions with a one-million-token context. The publisher does not offer a public checkpoint download. Provider: Meta. Access: Interface.
Aggregate Rating 1931 ± 33, rank #12 of 1640 rated models, from 66 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA CritPt | 32.86 | Accuracy (%) | 100 |
| AA GDP.pdf | 32.6 | All Criteria Pass Rate (%) | 100 |
| AutomationBench-AA - HR - Raw Objective Completion | 83.32 | Raw Objective Completion (%) | 100 |
| LLM Stats (DeepSWE 1.1) | 79 | Score (%) | 100 |
| LLM Stats (GDP.pdf) | 33.2 | Score (%) | 100 |
| LLM Stats (SWE-Marathon) | 57.5 | Score (%) | 100 |
| AA GDPval | 1857.09 | ELO | 99.7 |
| Artificial Analysis Intelligence Index | 55.8 | Intelligence Index | 99.6 |
| AA GDP.pdf - Legal - Criterion Pass Rate | 87.8 | Criterion Pass Rate (%) | 99.5 |
| AA GDP.pdf - STEM/Research - Criterion Pass Rate | 80.46 | Criterion Pass Rate (%) | 99.1 |
| AA-Briefcase - Analytical Quality Elo | 2116.26 | Elo | 99.1 |
| AA-Briefcase - XLSX - Rubric Pass Rate | 61.36 | Rubric Pass Rate (%) | 99.1 |
Interactive version: theaggregate.ai/model?slug=muse-wonder-full · How It Works · Data refreshed daily, snapshot 2026-10-13.